© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 9263
    Prev
    Next
    INDEX
    Explanations

    gold and its uses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ع
    1.40
    ہ
    1.37
    ت
    1.29
    ي
    1.25
    ாக
    1.21
    ان
    1.20
    an
    1.17
    ات
    1.17
    um
    1.13
    on
    1.13
    POSITIVE LOGITS
     I
    1.53
    0
    1.52
     the
    1.38
    ;
    1.25
    I
    1.22
    ],
    1.20
    1
    1.15
    ีย
    1.13
     of
    1.12
     Y
    1.09
    Activations Density 0.006%

    No Known Activations